{
 "critical_violations": [],
 "evaluated_utc": "2026-10-30T04:01:38.447226+00:00",
 "evaluator_version": "F3-dev-01/1.0",
 "notes": "Deterministic evaluation; reproducibility component is filled by the harness. Full-sample re-estimation leaks are NOT detectable on this series (documented in REFERENCE.md); the bound catches smoothing/foresight leaks.",
 "oracle_sha256": "3c7498c1f70346124c8233d46ab30a2eef957ec2e3437b34674287f93b43016a",
 "quality_components": {
  "baseline": 1.0,
  "correctness": 1.0,
  "integrity": 1.0,
  "reporting": 1.0,
  "reproducibility": 1.0
 },
 "quality_score": 1.0,
 "receipt_sha256": "316c1851986d82a485e328de56757793af04cdcf1cbf580282b8e10864edcab1",
 "required_criteria": [
  {
   "description": "Naive RMSE and MAE at h=1 equal the exact reference (rel 1e-6); 35 evaluated pairs (target 2025-10 missing)",
   "expected": {
    "mae_naive_h1": 0.09142857142857148,
    "rmse_naive_h1": 0.11710800875382403
   },
   "id": "naive_h1",
   "observed": {
    "mae_naive_h1": 0.09142857142857148,
    "rmse_naive_h1": 0.11710800875382403
   },
   "passed": true,
   "tolerance": {
    "mae_naive_h1": {
     "rel": 1e-06
    },
    "rmse_naive_h1": {
     "rel": 1e-06
    }
   }
  },
  {
   "description": "Naive RMSE and MAE at h=3 equal the exact reference (rel 1e-6)",
   "expected": {
    "mae_naive_h3": 0.12000000000000005,
    "rmse_naive_h3": 0.15856499343441843
   },
   "id": "naive_h3",
   "observed": {
    "mae_naive_h3": 0.12000000000000005,
    "rmse_naive_h3": 0.15856499343441843
   },
   "passed": true,
   "tolerance": {
    "mae_naive_h3": {
     "rel": 1e-06
    },
    "rmse_naive_h3": {
     "rel": 1e-06
    }
   }
  },
  {
   "description": "n_origins = 36, n_evaluated_h1 = 35, n_evaluated_h3 = 35",
   "expected": {
    "n_evaluated_h1": 35,
    "n_evaluated_h3": 35,
    "n_origins": 36
   },
   "id": "counts",
   "observed": {
    "n_evaluated_h1": 35,
    "n_evaluated_h3": 35,
    "n_origins": 36
   },
   "passed": true,
   "tolerance": {
    "n_evaluated_h1": {
     "abs": 0
    },
    "n_evaluated_h3": {
     "abs": 0
    },
    "n_origins": {
     "abs": 0
    }
   }
  },
  {
   "description": "forecasts.csv: 144 rows, target = origin + h, naive forecast = last observation <= origin, actual matches data",
   "expected": {
    "n_rows": 144
   },
   "id": "forecasts_chronology",
   "observed": {
    "actual_mismatches": 0,
    "model_rows": 72,
    "n_rows": 144,
    "naive_rows": 72
   },
   "passed": true,
   "tolerance": null
  },
  {
   "description": "model RMSE/MAE in results.json agree with forecasts.csv (rel 1e-5)",
   "expected": "recomputed from forecasts.csv",
   "id": "model_errors_consistent",
   "observed": {
    "h1": {
     "mae_from_csv": 0.09561928226000001,
     "mae_reported": 0.09561928226000001,
     "n": 35,
     "rmse_from_csv": 0.1197904141277979,
     "rmse_reported": 0.1197904141277979
    },
    "h3": {
     "mae_from_csv": 0.12090394601714284,
     "mae_reported": 0.12090394601714284,
     "n": 35,
     "rmse_from_csv": 0.15937419012351917,
     "rmse_reported": 0.15937419012351917
    }
   },
   "passed": true,
   "tolerance": {
    "rel": 1e-05
   }
  },
  {
   "description": "rel_improvement_rmse_h* = 1 - rmse_model/rmse_naive (abs 1e-6)",
   "expected": null,
   "id": "rel_improvement_consistent",
   "observed": {
    "h1": {
     "expected": -0.022905396501212927,
     "reported": -0.022905396501212927
    },
    "h3": {
     "expected": -0.005103249283300526,
     "reported": -0.005103249283300526
    }
   },
   "passed": true,
   "tolerance": {
    "abs": 1e-06
   }
  },
  {
   "description": "data_issues mentions the missing 2025-10 observation",
   "expected": "mention of 2025-10",
   "id": "data_issue_reported",
   "observed": "[{\"issue\": \"Missing observation(s) in UNRATE.csv: ['2025-10-01']\", \"handling\": \"Naive at origin 2025-10-01 uses the 2025-09-01 value; the ARIMA likelihood/filter skips the missing month; (origin,horizon) pairs targeting it are kept in forecasts.csv with empty actual and excluded from error statistic",
   "passed": true,
   "tolerance": null
  }
 ],
 "run_id": "RP0021",
 "schema_error": "",
 "schema_valid": true,
 "scientific_success": true,
 "task_id": "F3-dev-01"
}